Face normalization using multi-scale cortical keypoints
Autor(a) principal: | |
---|---|
Data de Publicação: | 2007 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.1/111 |
Resumo: | Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extractions. Simple, complex and end-stopped cells tuned to different spatial frequencies (scales) and/or orientations provide input for line, edge and keypoint detection. This yields a rich, multi-scale object representation that can be stored in memory in order to identify objects. The multi-scale, keypoint-based saliency maps for Focus-of-Attention can be explored to obtain face detection and normalization, after which face recognition can be achieved using the line/edge representation. In this paper, we focus only on face normalization, showing that multi-scale keypoints can be used to construct canonical representations of faces in memory. |
id |
RCAP_aa099f72f86cd9db1d87ab265a1ba4d4 |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/111 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Face normalization using multi-scale cortical keypointsVisão computorizadaCórtex visual621.38Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extractions. Simple, complex and end-stopped cells tuned to different spatial frequencies (scales) and/or orientations provide input for line, edge and keypoint detection. This yields a rich, multi-scale object representation that can be stored in memory in order to identify objects. The multi-scale, keypoint-based saliency maps for Focus-of-Attention can be explored to obtain face detection and normalization, after which face recognition can be achieved using the line/edge representation. In this paper, we focus only on face normalization, showing that multi-scale keypoints can be used to construct canonical representations of faces in memory.LisbonSapientiaCunha, JoãoRodrigues, J. M. F.du Buf, J. M. H.2009-02-13T17:09:38Z20072007-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfapplication/pdfhttp://hdl.handle.net/10400.1/111eng13th Portuguese Conference on Pattern Recognition (RECPAD 2007). - Lisbon, 26 October 2007. - 2 pAUT: JRO00913; DUB00865;info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-24T10:10:50Zoai:sapientia.ualg.pt:10400.1/111Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:54:32.201621Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Face normalization using multi-scale cortical keypoints |
title |
Face normalization using multi-scale cortical keypoints |
spellingShingle |
Face normalization using multi-scale cortical keypoints Cunha, João Visão computorizada Córtex visual 621.38 |
title_short |
Face normalization using multi-scale cortical keypoints |
title_full |
Face normalization using multi-scale cortical keypoints |
title_fullStr |
Face normalization using multi-scale cortical keypoints |
title_full_unstemmed |
Face normalization using multi-scale cortical keypoints |
title_sort |
Face normalization using multi-scale cortical keypoints |
author |
Cunha, João |
author_facet |
Cunha, João Rodrigues, J. M. F. du Buf, J. M. H. |
author_role |
author |
author2 |
Rodrigues, J. M. F. du Buf, J. M. H. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Sapientia |
dc.contributor.author.fl_str_mv |
Cunha, João Rodrigues, J. M. F. du Buf, J. M. H. |
dc.subject.por.fl_str_mv |
Visão computorizada Córtex visual 621.38 |
topic |
Visão computorizada Córtex visual 621.38 |
description |
Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extractions. Simple, complex and end-stopped cells tuned to different spatial frequencies (scales) and/or orientations provide input for line, edge and keypoint detection. This yields a rich, multi-scale object representation that can be stored in memory in order to identify objects. The multi-scale, keypoint-based saliency maps for Focus-of-Attention can be explored to obtain face detection and normalization, after which face recognition can be achieved using the line/edge representation. In this paper, we focus only on face normalization, showing that multi-scale keypoints can be used to construct canonical representations of faces in memory. |
publishDate |
2007 |
dc.date.none.fl_str_mv |
2007 2007-01-01T00:00:00Z 2009-02-13T17:09:38Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.1/111 |
url |
http://hdl.handle.net/10400.1/111 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
13th Portuguese Conference on Pattern Recognition (RECPAD 2007). - Lisbon, 26 October 2007. - 2 p AUT: JRO00913; DUB00865; |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf application/pdf |
dc.publisher.none.fl_str_mv |
Lisbon |
publisher.none.fl_str_mv |
Lisbon |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133144805277696 |